© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 386
    Prev
    Next
    INDEX
    Explanations

    information from a family history such as names, relationships, and dates

    oai_token-act-pair · gemini-2.0-flash

    family histories and biographies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    runOnUiThread
    -0.60
    )}</
    -0.59
    enumii
    -0.57
     BBM
    -0.55
     SKS
    -0.49
    ₂+
    -0.49
     sánh
    -0.49
    )}]{
    -0.49
     PRS
    -0.47
     SRL
    -0.47
    POSITIVE LOGITS
    MigrationBuilder
    0.71
     <<<<<<<<<<<<<<
    0.66
    LookAnd
    0.65
     GenerationType
    0.62
    Билгалдахарш
    0.59
    цезда
    0.56
    stdc
    0.55
    providedIn
    0.55
    :✨
    0.54
     cargas
    0.52
    Activations Density 5.675%

    No Known Activations